Research map / Learning theory and algorithms / Combinatorial and search optimization
Neural Guided Constraint Logic Programming for Program Synthesis
Lisa Zhang, Gregory Rosenblatt, Ethan Fetaya, Renjie Liao, William Byrd, Matthew Might, Raquel Urtasun, Richard Zemel
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use RNN constraint scoring instead of symbolic miniKanren search | miniKanren · Tree Manipulation Problems | Percent Solved: 27% -> 99% | Improved |
| use RNN constraint scoring instead of hand-tuned search heuristics | miniKanren · Tree Manipulation Problems | Percent Solved: 82% -> 99% | Improved |
| use RNN constraint guidance instead of input/output and partial-program embeddings (ablation) | neural-guided miniKanren · Tree Manipulation Problems | Percent Solved: 93% -> 99% | Improved |
| use RNN constraint guidance instead of input/output and partial-program embeddings (ablation) | neural-guided miniKanren · Tree Manipulation Problems | Average Steps: 46.7 -> 37.0 | Improved |
| use GNN rather than RNN to score constraints (ablation) | neural-guided miniKanren · Tree Manipulation Problems | Percent Solved: 99% -> 88% | Hurt |
| use GNN rather than RNN to score constraints (ablation) | neural-guided miniKanren · Tree Manipulation Problems | Average Steps: 37.0 -> 44.5 | Hurt |
| add constraint input to neural search guidance (ablation) | RNN-guided synthesis · Repeat(N), DropLast(N), BringToFront(N) | Largest N synthesized: 9 (time) -> 20+; 3 (time) -> 6 (time); 2 (time) -> 5 (time) | Improved |
| increase the number of GNN message-passing passes (ablation) | GNN-Guided + Constraints · Tree Manipulation Problems | Percent Solved | No clear effect |
| use average-pooling instead of min-pooling (ablation) | neural constraint scoring · Training | Gradient flow | Improved |
| expand two candidates per training step instead of one (ablation) | neural-guided synthesis · Training | Model robustness | Improved |
Closest papers by meaning
- Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples (ICLR 2018 · similarity 0.87)
- LogicMP: A Neuro-symbolic Approach for Encoding First-order Logic Constraints (ICLR 2024 · similarity 0.86)
- Program Synthesis via Test-Time Transduction (NeurIPS 2025 · similarity 0.85)
- HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis (NeurIPS 2024 · similarity 0.84)
- Constraints-Guided Diffusion Reasoner for Neuro-Symbolic Learning (AAAI 2026 · similarity 0.84)
- Is Programming by Example Solved by LLMs? (NeurIPS 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
